Abstract
Software reliability models are very useful to estimate the probability of the software fail along the time. Several different models have been proposed to predict the software reliability growth (SRGM); however, none of them has proven to perform well considering different project characteristics. The ability to predict the number of faults in the software during development and testing processes. In this paper, we explore Genetic Algorithms (GA) as an alternative approach to derive these models. GA is a powerful machine learning technique and optimization techniques to estimate the parameters of well known reliably growth models. Moreover, machine learning algorithms, proposed the solution overcome the uncertainties in the modeling by combining multiple models using multiple objective function to achieve the best generalization performance where. The objectives are conflicting and no design exists which can be considered best with respect to all objectives. In this paper, experiments were conducted to confirm these hypotheses. Then evaluating the predictive capability of the ensemble of models optimized using multi-objective GA has been calculated. Finally, the results were compared with traditional models.